Multi-Agent A2A with the Agent Development Kit(ADK), Azure ACI, and Gemini CLI

--- title: Multi-Agent A2A with the Agent Development Kit(ADK), Azure ACI, and Gemini CLI published: true series: Azure date: 2026-04-19 01:17:31 UTC tags: googleadk,multiagent,geminicli,a2a canonical_url: https://xbill999.medium.com/multi-agent-a2a-with-the-agent-development-kit-adk-azure-aci-and-gemini-cli-5fb746833a21 --- Leveraging the Google Agent Development Kit (ADK) and the underlying Gemini LLM to build Multi-Agent Applications with A2A protocol support using the Python programming language.  #### Aren’t There a Billion Python ADK Demos? Yes there are. Python has traditionally been the main coding language for ML and AI tools. The goal of this article is to provide a multi-agent test bed for building, debugging, and deploying multi-agent applications. #### What you talkin ‘bout Willis? So what is different about this lab compared to all the others out there? This is one of the first deep dives into a Multi-Agent application leveraging the advanced tooling of Gemini CLI. The starting point for the demo was an existing Codelab- which was updated and re-engineered with Gemini CLI. The original Codelab- is here: [Building a Multi-Agent System | Google Codelabs](https://codelabs.developers.google.com/codelabs/production-ready-ai-roadshow/1-building-a-multi-agent-system/building-a-multi-agent-system#0) #### What Is Python? Python is an interpreted language that allows for rapid development and testing and has deep libraries for working with ML and AI: [Welcome to Python.org](https://www.python.org/) #### Python Version Management One of the downsides of the wide deployment of Python has been managing the language versions across platforms and maintaining a supported version. The **pyenv** tool enables deploying consistent versions of Python: [GitHub - pyenv/pyenv: Simple Python version management](https://github.com/pyenv/pyenv) As of writing — the mainstream python version is 3.13. To validate your current Python: ```shell python --version Python 3.13.13 ``` #### Azure Container Instances [Azure Container Instances](https://www.google.com/search?q=Azure+Container+Instances&sca_esv=9e0af5be28576de2&rlz=1CAIWTJ_enUS1110&sxsrf=ANbL-n7o0MyASoiBM0kA0-E5qMMzLudrbw%3A1775144526115&ei=To7OadXFBoOYptQP9JuB0A8&biw=1396&bih=632&ved=2ahUKEwiIvt3awM-TAxUolYkEHTTxLJIQgK4QegYIAQgAEAM&uact=5&oq=azure+aci&gs_lp=Egxnd3Mtd2l6LXNlcnAiCWF6dXJlIGFjaTIKECMYgAQYJxiKBTILEAAYgAQYkQIYigUyBRAAGIAEMgcQABiABBgKMgUQABiABDIFEAAYgAQyBRAAGIAEMgYQABgWGB4yBhAAGBYYHjIGEAAYFhgeSOwPUABY2gxwAHgBkAEAmAGVAaABqQmqAQMwLjm4AQPIAQD4AQGYAgmgAvYJwgIKEAAYgAQYQxiKBcICDhAAGIAEGLEDGIMBGIoFwgIREC4YgAQYsQMY0QMYgwEYxwHCAhAQABiABBixAxhDGIMBGIoFwgILEC4YgAQYxwEYrwHCAg0QABiABBixAxhDGIoFwgIIEAAYgAQYsQPCAgsQABiABBixAxiDAZgDAJIHAzAuOaAHsFWyBwMwLjm4B_YJwgcFMi04LjHIBzuACAA&sclient=gws-wiz-serp) (ACI) is a serverless, managed service that allows you to run Docker containers in the cloud without managing virtual machines. It is ideal for rapid deployment, bursting, and simple, isolated applications, offering per-second billing and quick startup times. ACI supports Linux and Windows containers, with options for volume mounting and GPU resources. More details are available here: [https://azure.microsoft.com/en-us/products/container-instances](https://azure.microsoft.com/en-us/products/container-instances)  #### Why would I want Gemini CLI with Azure? Isn’t that a Google Thing? Yes- Gemini CLI leverages the Google Cloud console and Gemini models but it is also open source and platform agnostic. Many applications are already cross-cloud so this enables familiar tools to be run natively on Microsoft Azure. #### Azure Container Instance Configuration To configure your Azure Service with the base system tools- this article provides a reference: [MCP Development with Python, and the Azure Container Instance](https://xbill999.medium.com/mcp-development-with-python-and-the-azure-container-instance-2b7e7bbcdcfe) #### Gemini CLI If not pre-installed you can download the Gemini CLI to interact with the source files and provide real-time assistance: ```shell npm install -g @google/gemini-cli ``` #### Testing the Gemini CLI Environment Once you have all the tools and the correct Node.js version in place- you can test the startup of Gemini CLI. You will need to authenticate with a Key or your Google Account: ```plaintext ▝▜▄ Gemini CLI v0.33.1 ▝▜▄ ▗▟▀ Logged in with Google /auth ▝▀ Gemini Code Assist Standard /upgrade no sandbox (see /docs) /model Auto (Gemini 3) | 239.8 MB ``` #### Node Version Management Gemini CLI needs a consistent, up to date version of Node. The **nvm** command can be used to get a standard Node environment: [GitHub - nvm-sh/nvm: Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions](https://github.com/nvm-sh/nvm) #### Agent Development Kit The [Google Agent Development Kit](https://www.google.com/search?q=Google+Agent+Development+Kit&rlz=1CAIWTJ_enUS1114&oq=what+is+the+adk+google&gs_lcrp=EgZjaHJvbWUyBggAEEUYOTIICAEQABgWGB4yCAgCEAAYFhgeMggIAxAAGBYYHjIICAQQABgWGB4yCAgFEAAYFhgeMggIBhAAGBYYHjIKCAcQABgKGBYYHjINCAgQABiGAxiABBiKBTIKCAkQABiABBiiBNIBCDMxODlqMGo3qAIAsAIA&sourceid=chrome&ie=UTF-8&mstk=AUtExfB5Oo7ZHHcDEHu7aqZiPBA2l1c-QGh5dB7xkkDPIiYcn8O1Imt2IHNR7bzA6JnyDCSDCUGpGWTeBW14namlN_QqzJLLI5-px1BE9jfSxwli6njPDPERjm5pRqNP3uC6HhUKiRcTJ1T8x5LHQrCkVxylw7QWg0N8B4dQDIcWpnVX9Gc&csui=3&ved=2ahUKEwjYu-G8p-uSAxXrv4kEHUbpLo0QgK4QegQIARAB) (ADK) is an open-source, Python-based framework designed to streamline the creation, deployment, and orchestration of sophisticated, multi-agent AI systems. It treats agent development like software engineering, offering modularity, state management, and built-in tools (like Google Search) to build autonomous agents. The ADK can be installed from here: [Agent Development Kit (ADK)](https://google.github.io/adk-docs/) #### Agent Skills Gemini CLI can be customized to work with ADK agents. Both an Agent Development MCP server, and specific Agent skills are available. More details are here: [Agent Development Kit (ADK)](https://adk.dev/tutorials/coding-with-ai/) To get the Agent Skills in Gemini CLI: ```plaintext > /skills list Available Agent Skills: - adk-cheatsheet MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold). - adk-deploy-guide MUST READ before deploying any ADK agent. ADK deployment guide — Agent Engine, Cloud Run, GKE, CI/CD pipelines, secrets, observability, and production workflows. Use when deploying agents to Google Cloud or troubleshooting deployments. Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or project scaffolding (use adk-scaffold). - adk-dev-guide ALWAYS ACTIVE — read at the start of any ADK agent development session. ADK development lifecycle and mandatory coding guidelines — spec-driven workflow, code preservation rules, model selection, and troubleshooting. - adk-eval-guide MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold). - adk-observability-guide MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK observability guide — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations, and troubleshooting. Use when configuring monitoring, tracing, or logging for agents, or when understanding how a deployed agent handles real traffic. - adk-scaffold MUST READ before creating or enhancing any ADK agent project. Use when the user wants to build a new agent (e.g. "build me a search agent") or enhance an existing project (e.g. "add CI/CD to my project", "add RAG"). ``` and the ADK documentation: ```plaintext > /mcp list Configured MCP servers: 🟢 adk-docs-mcp (from adk-docs-ext) - Ready (2 tools) Tools: - mcp_adk-docs-mcp_fetch_docs - mcp_adk-docs-mcp_list_doc_sources ``` #### Where do I start? The strategy for starting multi agent development is a incremental step by step approach. First, the basic development environment is setup with the required system variables, and a working Gemini CLI configuration. Then, ADK Multi-Agent is built, debugged, and tested locally. Finally — the entire solution is deployed to Azure ACI. #### Setup the Basic Environment At this point you should have a working Python environment and a working Gemini CLI installation. All of the relevant code examples and documentation is available in GitHub. The next step is to clone the GitHub repository to your local environment: ```shell cd ~ git clone https://github.com/xbill9/gemini-cli-azure cd mulit-aci ``` Then run **init2.sh** from the cloned directory. The script will attempt to determine your shell environment and set the correct variables: ```shell source init2.sh ``` If your session times out or you need to re-authenticate- you can run the **set\_env.sh** script to reset your environment variables: ```shell source set_env.sh ``` Variables like PROJECT\_ID need to be setup for use in the various build scripts- so the **set\_env** script can be used to reset the environment if you time-out. Finally install the packages and dependencies: ```make make install ``` #### Verify The ADK Installation To verify the setup, run the ADK CLI locally with the researcher agent: ```shell xbill@penguin:~/gemini-cli-azure/multi-aci/agents$ adk run researcher /home/xbill/.local/lib/python3.13/site-packages/google/adk/features/_feature_decorator.py:72: UserWarning: [EXPERIMENTAL] feature FeatureName.PLUGGABLE_AUTH is enabled. check_feature_enabled() Log setup complete: /tmp/agents_log/agent.20260418_155613.log To access latest log: tail -F /tmp/agents_log/agent.latest.log {"asctime": "2026-04-18 15:56:13,235", "name": "root", "levelname": "INFO", "message": "Logging initialized for researcher", "filename": "logging_config.py", "lineno": 54, "service": "researcher", "log_level": "INFO"} {"asctime": "2026-04-18 15:56:13,236", "name": "researcher.agent", "levelname": "INFO", "message": "Initialized researcher agent with model: gemini-2.5-flash", "filename": "agent.py", "lineno": 85} ``` #### Test The ADK Web Interface This tests the ADK agent interactions with a browser: ```shell xbill@penguin:~/gemini-cli-azure/multi-aci/agents$ adk web --host 0.0.0.0 /home/xbill/.pyenv/versions/3.13.13/lib/python3.13/site-packages/google/adk/features/_feature_decorator.py:72: UserWarning: [EXPERIMENTAL] feature FeatureName.PLUGGABLE_AUTH is enabled. check_feature_enabled() 2026-04-10 17:49:11,850 - INFO - service_factory.py:266 - Using in-memory memory service 2026-04-10 17:49:11,850 - INFO - local_storage.py:84 - Using per-agent session storage rooted at /home/xbill/multi-agent/agents 2026-04-10 17:49:11,850 - INFO - local_storage.py:110 - Using file artifact service at /home/xbill/multi-agent/agents/.adk/artifacts /home/xbill/.pyenv/versions/3.13.13/lib/python3.13/site-packages/google/adk/cli/fast_api.py:198: UserWarning: [EXPERIMENTAL] InMemoryCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. credential_service = InMemoryCredentialService() /home/xbill/.pyenv/versions/3.13.13/lib/python3.13/site-packages/google/adk/auth/credential_service/in_memory_credential_service.py:33: UserWarning: [EXPERIMENTAL] BaseCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. super(). __init__ () INFO: Started server process [16063] INFO: Waiting for application startup. +-----------------------------------------------------------------------------+ | ADK Web Server started | | | | For local testing, access at http://0.0.0.0:8000. | +-----------------------------------------------------------------------------+ ``` Then use the web interface — either on the local interface **127.0.0.1** or the catch-all web interface **0.0.0.0** -depending on your environment:  Special note for Google Cloud Shell Deployments- add a CORS **allow\_origins** configuration exemption to allow the ADK agent to run: ```shell adk web --host 0.0.0.0 --allow_origins 'regex:.*' ``` #### Multi Agent Design The multi-agent deployment consists of 5 agents: - Researcher - Judge - Orchestrator - Content Builder - Course Builder An overview of the multi-agent system can be found here: [Multi-Agent A2A with the Agent Development Kit(ADK), Cloud Run, Agent Skills, and Gemini CLI](https://medium.com/google-cloud/multi-agent-a2a-with-the-agent-development-kit-adk-cloud-run-and-gemini-cli-52f8be838ad6) #### Running/Testing/Debugging Locally The main Makefile has been extended with extensive targets for managing the agents on the local development environment. The key targets include: ```make xbill@penguin:~/gemini-cli-azure/multi-aci$ make help Available commands: --- Local Development --- install - Install all dependencies for root, agents, and app start - Start all services locally (alias for start-local) stop - Stop all local services (alias for stop-local) run - Start all services locally status - Show status of local services local - Show local service URLs test - Run all tests (pytest) lint - Run linting checks (ruff) --- Azure ACI --- deploy-aci - Deploy all services to Azure Container Instances (ACI) destroy-aci - Delete ACI resources status-aci - Show ACI status (alias: az-status) endpoint-aci - Show ACI service endpoint (alias: endpoint) test-e2e-aci - Run ACI E2E test --- Shared Azure --- az-login - Login to Azure CLI acr-login - Login to ACR acr-create - Create/Verify ACR and Resource Group clean - Remove caches and logs ``` First check for local running agents: ```shell > make status ✦ I will run the make status command to check the status of your local services. ╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ ✓ Shell Running 'make status' to check local services. │ │ │ │ Checking status of locally running agents and servers... │ │ --- Network Status --- │ │ No services listening on expected ports (8000-8004, 5173). │ │ --- Process Status --- │ │ No matching processes found. │ │ │ ╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ ✦ No local services are currently running. ``` Then all the agents can be started together: ```shell make start ╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ ✓ Shell Starting all local services in the background. │ │ │ │ Stopping any existing agent and server processes... │ │ Starting all agents in background... │ │ Waiting for sub-agents to start... │ │ All agents started. Logs: researcher.log, judge.log, content_builder.log, orchestrator.log │ │ Starting App Backend in background... │ │ Starting Frontend dev server in background... │ │ All services started. Logs: researcher.log, judge.log, content_builder.log, orchestrator.log, backend.log, frontend.log │ │ Frontend: http://localhost:5173 │ │ Backend: http://localhost:8000 │ │ make status ╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ ✓ Shell Checking status of local services. │ │ │ │ ... first 22 lines hidden (Ctrl+O to show) ... │ │ dge/.well-known/agent-card.json; \ export CONTENT_BUILDER_AGENT_CARD_URL=http://localhost:8003/a2a/content_builder/.well-known/agent-card.jso │ │ n; \ /home/xbill/.pyenv/shims/python3 -m shared.adk_app --host 0.0.0.0 --port 8004 agents/orchestrator" │ │ xbill 14269 9.3 3.1 248416 148664 ? S 20:27 0:02 /home/xbill/.pyenv/versions/3.13.13/bin/python3 -m shared.adk_app --host 0.0 │ │ .0.0 --port 8004 agents/orchestrator │ │ xbill 14273 0.0 0.0 2584 1668 ? S 20:27 0:00 /bin/sh -c /bin/bash -c "source .env 2>/dev/null || true; \ export AGENT_SER │ │ VER_URL=http://localhost:8004; \ export AGENT_NAME=orchestrator; \ export PORT=8000; \ cd app && /home/xbill/.pyenv/shims/python3 main.py" │ │ xbill 14275 0.0 0.0 6940 3312 ? S 20:27 0:00 /bin/bash -c source .env 2>/dev/null || true; export AGENT_SERVER_URL=http:/ │ │ /localhost:8004; export AGENT_NAME=orchestrator; export PORT=8000; cd app && /home/xbill/.pyenv/shims/python3 main.py │ │ xbill 14278 8.4 3.1 1345296 144520 ? Sl 20:27 0:02 /home/xbill/.pyenv/versions/3.13.13/bin/python3 main.py │ ╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ ✦ The local agents and the backend server are running and listening on ports 8000-8004. The Vite dev server (port 5173) is still not appearing in the network status. ``` The entire project can be linted and tested as unit: ```shell > make lint ✦ I will run the make lint command to confirm that all linting checks pass. ╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ ✓ Shell Run linting checks to confirm they pass. │ │ │ │ ruff check . │ │ All checks passed! │ │ │ ╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ ✦ make lint completed successfully with no errors. > make test ✦ I will run the project's test suite using make test. ╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ ✓ Shell Run all tests using pytest. │ │ │ │ ... first 41 lines hidden (Ctrl+O to show) ... │ │ agents/orchestrator/agent.py:294 │ │ /home/xbill/gemini-cli-azure/multi-aci/agents/orchestrator/agent.py:294: UserWarning: [EXPERIMENTAL] RemoteA2aAgent: ADK Implementation for │ │ A2A support (A2aAgentExecutor, RemoteA2aAgent and corresponding supporting components etc.) is in experimental mode and is subject to breaki │ │ ng changes. A2A protocol and SDK are themselves not experimental. Once it's stable enough the experimental mode will be removed. Your feedbac │ │ k is welcome. │ │ content_builder = RemoteA2aAgent( │ │ │ │ -- Docs: [https://docs.pytest.org/en/stable/how-to/capture-warnings.html](https://docs.pytest.org/en/stable/how-to/capture-warnings.html) │ │ ====================================================== 30 passed, 4 warnings in 7.71s ======================================================= │ ╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ ✦ make test passed all 30 tests successfully. ``` And end to end tested: ```json ✓ Shell Running the end-to-end tests for the project. │ │ │ │ Running end-to-end test against http://localhost:8000... │ │ {"type": "progress", "text": "\ud83d\ude80 Connected to backend, starting research..."} │ │ {"type": "progress", "text": "\ud83d\ude80 Starting the course creation pipeline..."} │ │ {"type": "progress", "text": "\ud83d\udd0d Research is starting..."} │ │ {"type": "progress", "text": "\ud83d\udd0d Researcher is gathering information..."} │ │ {"type": "progress", "text": "\u2696\ufe0f Judge is evaluating findings..."} │ │ {"type": "progress", "text": "\u2696\ufe0f Judge is evaluating findings..."} │ │ {"type": "progress", "text": "\u270d\ufe0f Building the final course content..."} │ │ {"type": "progress", "text": "\u270d\ufe0f Content Builder is writing the course..."} │ ``` Then connect to the local front end:  And the entire agent system will run in the local environment:  #### Local Logging / Debugging Gemini CLI has full access to the local agent logs for debugging and troubleshooting: ```plaintext ✦ I've analyzed the logs from your e2e run. All agents (researcher, judge, content_builder, orchestrator) and both frontend and backend services started successfully. The course creation pipeline ran as expected: the orchestrator initiated the "history of the internet" course, the researcher gathered information, the judge approved it, and the content builder generated the course content. ``` #### Deploying to Azure ACI The project level Makefile has targets for managing the Agent deployment to serverless endpoints: ```shell xbill@penguin:~/gemini-cli-azure/multi-aci$ az login A web browser has been opened at https://login.microsoftonline.com/organizations/oauth2/v2.0/authorize. Please continue the login in the web browser. If no web browser is available or if the web browser fails to open, use device code flow with `az login --use-device-code`. ``` A utility script check the deployment to Azure ACI: ```shell xbill@penguin:~/gemini-cli-azure/multi-aci$ make status-aci ./aci/status-aci.sh Checking Azure Container Instances status in adk-rg-aci... (ResourceGroupNotFound) Resource group 'adk-rg-aci' could not be found. Code: ResourceGroupNotFound Message: Resource group 'adk-rg-aci' could not be found. make: *** [Makefile:202: status-aci] Error 3 ``` You can then deploy the services: ```shell xbill@penguin:~/gemini-cli-azure/multi-aci$ make deploy ./aci/deploy-aci.sh === Azure ACI Deployment === Azure Location: westus2 Resource Group: adk-rg-aci ACR Name: adkacrpenguin ============================= Ensuring Resource Group exists... Location Name ---------- ---------- westus2 adk-rg-aci Ensuring ACR exists... ✦ I have successfully rebuilt the ACI deployment by consolidating the microservices into a single Azure Container Group and enabling Log Analytics integration. ``` Once the containers are deployed- you can then get the endpoint: ```shell And check the endpoint: │ ✓ Shell make aci-status │ │ │ │ ./aci/status-aci.sh │ │ Checking Azure Container Instances status in adk-rg-aci... │ │ Name FQDN IP │ │ -------------------- ------------------------------------------------------ -------------- │ │ course-creator-group course-creator-group-penguin.westus2.azurecontainer.io 172.179.100.61 │ │ xbill@penguin:~/gemini-cli-azure/multi-aci$ make endpoint ./aci/endpoint-aci.sh --- Azure ACI Endpoint --- http://course-creator-group-penguin.westus2.azurecontainer.io:8080/ xbill@penguin:~/gemini-cli-azure/multi-aci$ ``` The service will be visible in the Azure console:  #### Test End to End in ACI The entire agent system is tested on the remote Azure endpoint: ```shell ✦ The make endpoint-aci command has successfully retrieved and displayed the public URL for the Azure Container App. > make e2e-test-aci ✦ The end-to-end test against the newly deployed Azure Container Group was successful. The system correctly orchestrated the research, evaluation, and content generation phases, producing a structured course on the history of the internet. ``` #### Running the Web Interface Start a connection to the Cloud Run deployed app: ```plaintext http://course-creator-group-penguin.westus2.azurecontainer.io:8080/ ``` Then connect to the app :  Then use online course generator:  #### Final Gemini CLI Code Review As a final step — Gemini CLI was used for a full code review of the project: ```plaintext ✦ I have successfully rebuilt the ACI deployment by consolidating the microservices into a single Azure Container Group and enabling Log Analytics integration. Summary of Actions - Cleanup: Destroyed the five individual container instances to transition to a grouped deployment. - Image Rebuild: Built and pushed new versions of all five microservice images (researcher, judge, content-builder, orchestrator, and course-creator) to the Azure Container Registry with the latest tag. - Logging Configuration: Successfully retrieved the workspace ID and primary key for the existing adk-log-workspace Log Analytics workspace. - Group Deployment: Deployed the course-creator-group container group using the generated aci-container-group.yaml, ensuring all containers share the same network and lifecycle while streaming logs to Azure Monitor. Deployment Details - Container Group Name: course-creator-group - Resource Group: adk-rg-aci - Region: westus2 - Public URL: http://course-creator-group-penguin.westus2.azurecontainer.io:8080 (http://course-creator-group-penguin.westus2.azurecontainer.io:8080) - Logging: Integrated with Log Analytics workspace adk-log-workspace. Key Achievements - Container Group Deployment: The multi-agent system is now running efficiently as a single container group in ACI, reducing overhead and simplifying inter-agent communication via localhost. - Integrated Logging: Log Analytics is active, providing centralized monitoring for all microservices. - Verified Functionality: The e2e-test-aci confirmed that the orchestrator can successfully communicate with the sub-agents and the main application remains fully functional in the Azure environment. The deployment is now fully optimized and verified. ``` #### Summary The Agent Development Kit (ADK) was used to build a multi-agent system with A2A support using the Gemini Flash LLM Model. This application was tested locally with Gemini CLI and then deployed to Azure ACI. Several key take-aways and lessons learned were summarized from debugging and testing the multi-agent system- including deep log reviews. Finally, Gemini CLI was used for a complete project code review.